Scalable and Accurate Subsequence Transform - Université Clermont Auvergne Accéder directement au contenu
Article Dans Une Revue Pattern Recognition Année : 2023

Scalable and Accurate Subsequence Transform

Résumé

Time series classification using phase-independent subsequences called shapelets is one of the best approaches in the state of the art. This approach is especially characterized by its interpretable property and its fast prediction time. However, given a dataset of n time series of length at most m, learning shapelets requires a computation time of O(n 2 m 4) which is too high for practical datasets. In this paper, we exploit the fact that shapelets are shared by the members of the same class to propose the SAST (Scalable and Accurate Subsequence Transform) algorithm which is interpretable, accurate and more faster than the actual state of the art shapelet algorithm. The experiments we conducted on the UCR archive datasets shown that SAST is more accurate than the state of the art Shapelet Transform algorithm on many datasets, while being significantly more scalable.
Fichier principal
Vignette du fichier
sast.pdf (1.73 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-03087686 , version 1 (24-12-2020)
hal-03087686 , version 2 (02-03-2022)
hal-03087686 , version 3 (21-11-2023)

Licence

Identifiants

Citer

Michael F Mbouopda •, Engelbert Mephu. Scalable and Accurate Subsequence Transform. Pattern Recognition, 2023, 147, pp.1-18. ⟨10.1016/j.patcog.2023.110121⟩. ⟨hal-03087686v3⟩
364 Consultations
270 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More